Update app.py

app.py

@@ -1,52 +1,71 @@
 import gradio as gr
 from transformers import pipeline
 
-# Create a pipeline with the GPT-2 model (openai-community/gpt2)
-pipe = pipeline("text-generation", model="openai-community/gpt2")
-
-def generate_mermaid_code(text_description):
-    """
-    Generate Mermaid.js code from a text description using the GPT-2 model.
-    Args:
-        text_description (str): A textual description of the process or flow.
-    Returns:
-        str: Generated Mermaid.js code.
-    """
-    # Define the conversation with the user as a message
-    messages = [
-        {"role": "user", "content": f"Convert the following process description into Mermaid.js code: {text_description}"},
-    ]
-    
-    # Use the model to generate Mermaid.js code
-    generated_text = pipe(messages[0]['content'], max_length=150, num_return_sequences=1)[0]['generated_text']
-    
-    # Return the generated Mermaid.js code
-    return generated_text.strip()
-
-# Create the Gradio interface
-with gr.Blocks() as demo:
-    gr.Markdown("# Process Flow to Mermaid.js Code Generator")
-    
-    with gr.Row():
-        with gr.Column():
-            # Input text description from the user
-            text_description = gr.Textbox(
-                label="Enter Process Description",
-                placeholder="Describe the process flow here..."
-            )
-        with gr.Column():
-            # Output Mermaid.js code
-            mermaid_code = gr.Textbox(
-                label="Generated Mermaid.js Code",
-                interactive=False,
-                placeholder="The Mermaid.js code will appear here..."
-            )
-    
-    # Button to trigger Mermaid.js code generation
-    generate_btn = gr.Button("Generate Mermaid Flowchart")
-    
-    # Define action on button click: generate the Mermaid code
-    generate_btn.click(fn=generate_mermaid_code, inputs=[text_description], outputs=mermaid_code)
+# Initialize pipelines for text generation and speech recognition
+text_generation_pipeline = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.2")
+speech_recognition_pipeline = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3-turbo")
+
+# Function to transcribe audio using the Whisper pipeline
+def transcribe_audio(audio_file):
+    try:
+        # Use the Whisper pipeline for automatic speech recognition
+        transcription = speech_recognition_pipeline(audio_file)
+        return transcription.get("text", "Transcription not available.")
+    except Exception as e:
+        return f"Error in transcription: {e}"
+
+# Function to generate Mermaid.js code using the Mistral pipeline
+def generate_mermaid_code(prompt):
+    try:
+        # Use the text-generation pipeline to generate Mermaid.js code
+        result = text_generation_pipeline(
+            prompt, 
+            max_length=256, 
+            temperature=0.7, 
+            num_return_sequences=1
+        )
+        return result[0]["generated_text"].strip() if result else "No Mermaid.js code generated."
+    except Exception as e:
+        return f"Error in Mermaid.js generation: {e}"
+
+# Function to process input (text, audio, or both)
+def process_input(input_type, text_input, audio_input):
+    try:
+        if input_type == "Audio" and audio_input:
+            transcription = transcribe_audio(audio_input)
+            return generate_mermaid_code(transcription)
+
+        elif input_type == "Text" and text_input:
+            return generate_mermaid_code(text_input)
+
+        elif input_type == "Text and Audio" and text_input and audio_input:
+            transcription = transcribe_audio(audio_input)
+            combined_input = f"{text_input} and {transcription}"
+            return generate_mermaid_code(combined_input)
+
+        else:
+            return "Please provide valid input."
+    except Exception as e:
+        return f"Error: {e}"
+
+# Set up the Gradio interface
+iface = gr.Interface(
+    fn=process_input,
+    inputs=[
+        gr.Radio(["Text", "Audio", "Text and Audio"], label="Input Type", value="Text"),
+        gr.Textbox(lines=10, label="Text Input", placeholder="Enter task flow description here..."),
+        gr.Audio(type="filepath", label="Audio Input"),
+    ],
+    outputs=[
+        gr.Textbox(lines=20, label="Generated Mermaid.js Code"),
+    ],
+    title="Mermaid.js Generator",
+    description=(
+        "Provide text, audio, or both."
+        "Mermaid.js code will be generated for text or audio input, or their combination."
+    ),
+)
 
 # Launch the Gradio app
-demo.launch()
+if __name__ == "__main__":
+    iface.launch()